33 results about "Fuzzy expert system" patented technology

The invention provides a device and a method for intelligent terms conversion. The device comprises a DSP central processing chip, a memory module, a display and keyboard operation module and an uplink-downlink communication module, wherein the memory module, the display and keyboard operation module and the uplink-downlink communication module are connected with the DSP central processing modulerespectively, a front-end computer communication module is connected with a front-end computer through a RS-232 bus, a RS-232 communication module is connected with a plurality of sub-stations RTU bya serial expansion circuit, a term converter is arranged between the RTU and the front-end compute of a power communication system, the uploaded communication protocol of the sub-stations RTU are intelligently recognized by a fuzzy expert system, the format of the recognized terms are converted into a unified terms format, uploaded to the front-end computer, and uploaded to each level of workstation by the front-end computer. The invention has the advantages that operators can realize automatic recognition and conversion of terms of interconnected two parties by the device without knowing theterms types of the interconnected two parties, thus avoiding the error possibly brought by manual operation.

The invention discloses a method for predicting residual service life of a flight control computer system, which comprises the steps of: storing historical reliability data of the flight control computer system by using an onboard health monitoring computer, obtaining working state data, and executing failure detection, reliability analysis and service life prediction of the flight control computer by using a fuzzy expert system. The working state data is obtained from a state sensor group. The development of the fuzzy expert system is used for modeling the reliability of the flight computer system, and the working condition of the flight control computer system is estimated according to the working state data and the fuzzy based reasoning for carrying out failure detection and predicting residual service life. The invention has the advantage of being capable of estimating the residual service life of the flight control computer system on line.

A method for automatic generation of a Neuro-Fuzzy Expert System (Fuzzy Logic Expert System implemented as a Neural Network) from data. The method comprising a Data Interface allowing description of location, type, and structure of the Data. The Interface also allows designation of input attributes and output attributes in the Data Structure; automatic Neuro-Fuzzy Expert System generation driven by the Data; Training of the Expert System's Neural Network on the Data and the presentation of results which include new knowledge embedded in the parameters and structure of the trained Neuro-Fuzzy Expert System to a user.

The invention relates to a self-adaptive light source lighting system and a self-adaptive light source lighting method for a high-precision image measuring device. The system comprises a light source and a control system, wherein the light source comprises a front light source and a back light source; the control system comprises a microprogrammed control unit (MCU) module, a digital-to-analogue conversion module, a lighting driving module, a serial port communication module and a fuzzy expert system. In the invention, an MCU module is connected with the lighting driving module through the digital-to-analogue conversion module; the serial port communication module performs data exchange with a master personal computer (PC); the PC and the control system form a 'master-slave' lighting control system; the master PC runs a man-machine interface for lighting control and has a built-in fuzzy expert system module and an optimal lighting parameter fuzzy database. When a workpiece is measured, the control system automatically select optimal lighting parameters according to the characteristic parameters of the workpiece to be measured, so the self-adaptive control over the brightness of channel light sources is realized and an image measurement instrument can acquire an optimal image.

The invention relates to a motor optimization design method for a multi-objective particle swarm optimization algorithm based on a fuzzy expert system. The method performs motor optimization design by adopting the multi-objective particle swarm optimization algorithm based on the object distance, utilizes the fuzzy expert system to introduce expertise experiences for the motor design in and guide the particle swarm to move towards the optimum solution set and finally obtains the optimum solution set of the motor design. Since the invention utilizes the expertise experiences to guide the particle swarm to move towards the optimum solution set, the influence of the initial solution selected at random to the solving result is reduced, the precision and the speed of solution of the multi-objective particle swarm optimization algorithm are improved, and the development cycle is quickened.

The invention provides an oil well working fluid level self-adaptive prediction method based on fuzzy evaluation, and relates to the technical field of petroleum production. Firstly,establishing a multi-working-condition prediction model according to production working conditions of an oil field, adopting a reinforcement learning algorithm for different working conditions to establish sub-models,and matching an optimal working condition output model according to different production characteristics; dynamically determining a weighted weight of the integrated sub-model; establishing a fuzzy expert system related to liquid production fluctuation change trend reasoning by utilizing the working fluid level data and the pump efficiency parameters of the on-line measurement output model, and evaluating the working condition model; and performing online self-adaptive updating modeling by utilizing a new model performance evaluation index of fuzzy evaluation, and dynamically updating the model by judging the fitting goodness of the fluctuation change trend of the liquid production amount and an actual value. According to the oil well working fluid level self-adaptive prediction method based on fuzzy evaluation, the defects that when a single model algorithm is used for working fluid level prediction, the prediction precision is not high, the generalization performance is poor, overfitting is likely to happen and the like are effectively overcome.

The invention relates to an electric transmission line icing state assessment method based on the BP neural network and a fuzzy expert system. The method comprises the following steps that (1), ambient temperature and ambient relative humidity are obtained, whether the temperature and the humidity reach an icing condition is judged, and if yes, the step (2) is executed; (2), ambient temperature different delta T, icing duration F and icing thickness H are obtained, and the icing weighted value of ambient temperature difference, the icing weighted value of equivalent icing thickness and the icing weighted value of icing duration are calculated out; (3), the BP neutral network is used for carrying out data fusion on the icing weighted values, the line icing probability is calculated out, if the line icing probability is 0, an output line is not iced, and if the line icing probability is 1, the step (4) is executed; (4), the ambient temperature different delta T, the icing duration F and the icing thickness H obtained in the step (2) are used as input of the fuzzy expert system, and assessment results are output through fuzzy reasoning. Compared with the prior art, the method has the advantages of being precise in assessment and the like.

The invention provides a mass spectrum system used for detecting biomolecules. The system comprises a mass spectrometer data collecting system, an intelligent fuzzy expert system, a knowledge base collecting system and a model collecting system. The mass spectrometer data collecting system is used for detecting mass spectrum data of a sample; the intelligent fuzzy expert system can carry out intelligent analysis on the mass spectrometer data; the knowledge base collecting system can store and manage related knowledge of mass spectrum detection in advance through a cloud center; the model collecting system is used for sending the known mass spectrum model data to a knowledge management system and a mass spectrum model storage device according to instructions. The system is supported by cloud center calculation, intelligent learning and storage are performed through the knowledge base collecting system, the intelligent analysis is carried out on the mass spectrum data through the intelligent fuzzy expert system, and simulation with lower cost is carried out to generate a large amount of training data; the system is conductive to analyzing large samples, is suitable for nonprofessional operations, achieves monitoring personal health information in real time, and meets personalized medical service requirements.

The invention relates to a ceramic wall and floor tile flatness detection device and method, and the device includes an illumination module and an acquisition module. The illumination module includesa grid-shaped dense laser mounted above a detection area; and the acquisition module includes a camera mounted above the detection area. The ceramic wall and floor tile flatness detection device usesgrid-shaped dense laser to irradiate the surface of a ceramic tile in a direction perpendicular to the surface of the ceramic tile, thereby obtaining a ceramic wall and floor tile with evenly distributed surface grids; utilizes the acquisition module, acquires image data of the ceramic wall and floor tile through a CCD camera, and sends the image data to a positioning module; based on the positioning module, locates a deformation area of the image data and sends to a calculation module, adopts a BP neural network to process the deformation area, and calculates the flatness of the surface of the ceramic wall and floor tile where deformation occurs; and finally, utilizes a grading module, and adopts a quality fuzzy expert system to realize quality grading of the ceramic wall and floor tile,so as to solve the problem of low detection accuracy of surface flatness of the ceramic wall and floor tile.

In the method according to the invention a phonocardiographic signal, obtained by a passive acoustic sensor (10) from a maternal abdominal wall, is pre-filtered, amplified, digitized, digitally filtered by means of a programmable amplifier and filter unit (20), is stored in an intermediate memory and autocorrelation is performed by means of an autocorrelation unit (30) in a time window of a predetermined size. The signals obtained as a result of autocorrelation are fed to an input of a fuzzy expert system (40), wherein local maximums of the signals, temporal location of the local maximums and variation of the temporal location of the local maximums are determined by the fuzzy expert system (40), and, applying those as input parameters or signals of the fuzzy expert system, those are classified into probability groups utilizing a fuzzy rule set of a decision logic stored in a knowledge base and biologically expected data and are evaluated.

The invention discloses a power-quality (PQ) governance decision support method based on a fuzzy expert system. The method includes collection, calculation, analysis and counting of power-quality index deviation information of a target power network, cost-benefit analysis and evaluation of all steady-state power-quality index deviations, input variable definition and fuzzification of the decisionexpert system, output variable definition and fuzzification of the decision expert system, establishment of a fuzzy expert rule library based on production-type rules, construction of a fuzzy reasoning mechanism of the decision expert system and output and interpretation of a decision support result.

This invention discloses one traffic control system and method on harbor, which comprises interface module, data read and process module, interface display module, integration information module and decision formula module. This invention comprises the following steps: dynamically describing car flow with its main situations reflected by the car position, car speed and channel and speeding behavior; establishing one distribution blur special system module to determine car real speed, channel switch or speeding according to the knowledge and blur inductance method.

The invention discloses a bearing fault diagnosis method based on a data driving and random intuitive fuzzy strategy. The method comprises the following steps that (1) a massive data idea is used for building a fuzzy expert system, and data driving is realized; (2) the fault feature membership degree of a bearing to be inspected is built; (3) random fuzzy set matching and intuitive fuzzy decision fusion are carried out. According to the bearing fault diagnosis method, mass experiment data is used as the basis, the frequency spectrum analysis is carried out, and the feature frequency is found through the amplitude value occurring position. In addition, the fuzzy evidence is fused and converted into the random fuzzy set matching and intuitive fuzzy set decision. The uncertainty information is a part of energy of frequency spectrum information, and the objectiveness is lost when the evidence theory is directly omitted. The energy loss is sufficiently considered by the intuitive fuzzy strategy.

The invention provides a quality control method of caviar in a processing course. The quality control method comprises the following steps: obtaining the standard attribute parameters of the caviar to be processed, wherein the standard attribute parameters comprise the variety and the grade of the caviar; according to the standard attribute parameters, obtaining the mark information of sturgeons to be processed from an attribute database of raw materials namely the sturgeons, wherein the attribute database of the raw materials namely the sturgeons comprises the corresponding relation of the mark information of the raw materials namely the sturgeons and the standard attribute parameters, and the mark information is used for reflecting the attribute of the raw materials namely the sturgeons; according to the mark information of the sturgeons to be processed, obtaining sturgeon roes; determining the pickling time of the sturgeon roes by using a fuzzy expert system; and pickling the cleaned sturgeon roes for the pickling time so as to obtain the caviar. The quality control method disclosed by the invention can ensure the quality of the caviar.

The invention discloses a fuzzy expert system-based fan safety chain fault analysis method and system. The method comprises the steps of collecting all operation data of safe operation of a wind driven generator; performing fault analysis on the operation data by using a fuzzy expert system; and if a the set has a fault in operation, performing emergency shutdown, and making the set offline. The fault analysis is performed on the safe operation data of the wind generating set by utilizing the fuzzy expert system to determine a fault occurrence type, and with the combination of historical data in a certain time period, the fault analysis accuracy is improved, and the fault maintenance time is shortened; and the system further has a data display function, so that a worker can conveniently check the operation state at any time.

The invention relates to a flotation dosing self-adaptive regulation and control method which is characterized by comprising the following steps: collecting detection data D1 in a flotation process, establishing a comprehensive database, fusing the detection data D1 and historical data to form to-be-integrated data D2 for integration, and constructing a GRNN neural network prediction model. Inputting training data, comparing the training data with the concentrate grade and the metal recovery rate in a historical database, and reasoning by adopting a fuzzy expert system and utilizing a Mamdani fuzzy inference engine to obtain an agent addition amount; taking the obtained agent addition amount and detection data D1 collected in real time as input sample data B of a GRNN neural network prediction model, and obtaining predicted concentrate grade and metal recovery rate data Y; s6, judging whether requirements are met or not, if the requirements are met, executing the current dosage, and if the requirements are not met, returning to the fuzzy expert system for reasoning again, and repeating the operations of S4, S5 and S6. The stability of the flotation concentrate grade is achieved, and the optimal metal recovery rate is obtained.